Skip to main content

A small example package

Project description

moModelAnalysisTool

准备工作

pip install pqi
pqi use pypi 
pip install momodeltool / pip install momodeltool --upgrade

Visualization模块

通道可视化模块,使用举例:

from momodeltool import Visualization

'''使用开关'''
def forward(self, x):
  out = layer1(x)
  visual = Visualization()
  visual.switch_control()  # 打开展示开关,展示layer1
  visual.show_layer(out, module_name='layer1', show=True, save='./', pseudo=True, hist=True)
  visual.switch_control()  # 关闭展示开关,不展示layer2
  visual.show_layer(out, module_name='layer2', show=True, save='./', pseudo=True, hist=True) 
  out = layer2(out)
  visual.destroyAllWindows()  # 任意键入,关闭所有窗口

'''使用静态方法'''
def forward(self, x):
  out = layer1(x)
  Visualization.layer_show(out, module_name='layer1', show=True, save='./', pseudo=True, hist=True, norm=True, mode=2)  # 展示layer1,任意键入,关闭相关窗口 norm归一话开关 mode=1归一化针对展示的全图,mode=2归一化针对全图中的单个图像
  out = layer2(out)

model.load_state_dict()
Visualization.kernel_show(model, module_name='test', show=Ture, save='./')

展示样例
Alt text Alt text

ModelProcess模块

网络模型处理模块,使用样例:

from momodeltool import ModelProcess

mp = ModelProcess()
model = stereonet(batch_size=1, cost_volume_method=cost_volume_method)
pretrained_model_path = "mypath/model_1340.pth"
new_model = mp.auto_adapt(model, pretrained_model_path)  # 自动调整权重
mp.show_keys(new)  # 展示模型权重key

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

momodeltool-0.0.17.tar.gz (508.2 kB view details)

Uploaded Source

Built Distribution

momodeltool-0.0.17-py3-none-any.whl (12.8 kB view details)

Uploaded Python 3

File details

Details for the file momodeltool-0.0.17.tar.gz.

File metadata

  • Download URL: momodeltool-0.0.17.tar.gz
  • Upload date:
  • Size: 508.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.8.18

File hashes

Hashes for momodeltool-0.0.17.tar.gz
Algorithm Hash digest
SHA256 7a96406c4b3053f11d0c436c2dcceb518952405707d4b42043cd52003c1c26d4
MD5 849944a31620e2e943ae793173d4b3e1
BLAKE2b-256 9872bfc98446cd15cb2cf3f1f8947e44d0e4316598c8788991e718bc54691695

See more details on using hashes here.

File details

Details for the file momodeltool-0.0.17-py3-none-any.whl.

File metadata

  • Download URL: momodeltool-0.0.17-py3-none-any.whl
  • Upload date:
  • Size: 12.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.8.18

File hashes

Hashes for momodeltool-0.0.17-py3-none-any.whl
Algorithm Hash digest
SHA256 15783c521fe60c7a22207fa5a65fb1ba45f6245a4d4d6a617f5f02ff7f294709
MD5 784b85237eaaa6c6da7a6b3b7bab51f1
BLAKE2b-256 c9703b017d66277fcfd1daa35b463ab62e841ce4853ef082a278e3c5a5e822f7

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page